Announcement for Downloading full text filePlease respect the Copyright Act.
All digital full text dissertation and theses from this website are authorized the copyright owners. These copyrighted full-text dissertation and theses can be only used for academic, research and non-commercial purposes. Users of this website can search, read, and print for personal usage. In respect of the Copyright Act of the Republic of China, please do not reproduce, distribute, change, or edit the content of these dissertations and theses without any permission. Please do not create any work based upon a pre-existing work by reproduction, Adaptation, Distribution or other means.
URN etd-0719113-153807 Statistics This thesis had been viewed 1572 times. Download 583 times. Author Po-Chun Huang Author's Email Address No Public. Department Computer Science and Enginerring Year 2012 Semester 2 Degree Master Type of Document Master's Thesis Language zh-TW.Big5 Chinese Page Count 45 Title AN ENHANCED XEN SCHEDULER USING IMPROVED D_EDF SCHEDULING ALGORITHM Keyword Earliest Deadline First Scheduling Algorithm Virtualization Xen Xen Virtualization Scheduling Algorithm Earliest Deadline First Abstract With the development of cloud computing, mobile device and industry automation, virtualization plays an important role today. The core of virtualization is hypervisor which directly determines the performance of platform. Therefore, how to allocate resource effectively becomes an important issue.
Xen, one of widely used open source projects, is a virtual machine monitor. Simple EDF (Earliest Deadline First) scheduler that is a dynamic-priority real-time scheduler in Xen implements the famous EDF scheduling algorithm. Due to EDF scheduling strategy has miss the deadline and inefficiency in overloaded condition, we have improved the D_EDF scheduling algorithm that combine Deadline-Monotonic scheduling strategy with EDF scheduling in virtualized environment. And we have extended the Simple EDF scheduler which provided by Xen using improved D_EDF scheduling algorithm. Our experiment demonstrates that the proposed scheduling algorithm present increase the performance under CPU-intensive and memory-intensive workload in overloaded condition. The benchmark time of proposed scheduling algorithm is only 78% that of Simple EDF scheduler. And the kernel latency of proposed scheduling algorithm is approximately 83% that of Simple EDF scheduler in overloaded condition.
Advisor Committee Chia-Ying Tseng - advisor
Liang-Teh Lee - co-chair
Trong-Yen Lee - co-chair
Files Date of Defense 2013-07-04 Date of Submission 2013-07-19